Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1 @@
+{"<e>": 250002, "</e>": 250003}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250004
+}

eval_results.txt

@@ -0,0 +1,20 @@
+accuracy = 0.9292929292929293
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.9767    0.8750    0.9231        48
+         1.0     0.8929    0.9804    0.9346        51
+
+    accuracy                         0.9293        99
+   macro avg     0.9348    0.9277    0.9288        99
+weighted avg     0.9335    0.9293    0.9290        99
+
+eval_loss = 0.2525997969160716
+fn = 1
+fp = 6
+macro_f1 = 0.9288281811646297
+mcc = 0.8624674813241404
+tn = 42
+tp = 50
+weighted_f1 = 0.929002461712742
+weighted_p = 0.9348006644518272
+weighted_r = 0.9276960784313726

model_args.json

@@ -0,0 +1 @@
+{"adam_epsilon": 1e-08, "begin_tag": "<e>", "best_model_dir": "best_model/zh_zh", "cache_dir": "temp/cache_dir/", "config": {}, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 70, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 10, "encoding": null, "end_tag": "</e>", "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": false, "evaluate_during_training_steps": 20, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 20, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 120, "model_name": "xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "num_train_epochs": 5, "output_dir": "temp/outputs/", "overwrite_output_dir": true, "process_count": 70, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 20, "save_recent_only": true, "silent": false, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": false, "wandb_kwargs": {"group": "zh_zh_xlm-roberta-large_BT_concat", "job_type": "2"}, "wandb_project": "TransWiC-groups", "warmup_ratio": 0.1, "warmup_steps": 56, "weight_decay": 0, "skip_special_tokens": true, "model_class": "ClassificationModel", "labels_list": [0, 1], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "stride": 0.8, "tie_value": 1, "tagging": true, "strategy": "BT", "special_tags": ["<e>"], "merge_n": 2, "merge_type": "concat"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120eff9134c89aab615752718c6b909dbdac3e6b0c2ae9264ef327289826872f
+size 4504578173

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c47393b1826feccd7f2ae138246ecdf8eb7ee95837139d4d919a2ba35018e4
+size 2256539453

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34838c2fe62d16562347410eb01ff71034f937e4b060815f4e9c75fdac7e4128
+size 627

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

test_eval.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.5645    0.5780    0.5711       500
+           T     0.5676    0.5540    0.5607       500
+
+    accuracy                         0.5660      1000
+   macro avg     0.5660    0.5660    0.5659      1000
+weighted avg     0.5660    0.5660    0.5659      1000
+
+
+ADJ
+Accuracy = 0.532258064516129
+Weighted Recall = 0.532258064516129
+Weighted Precision = 0.5577523413111342
+Weighted F1 = 0.5382974202048536
+Macro Recall = 0.5339912280701754
+Macro Precision = 0.532258064516129
+Macro F1 = 0.5262187088274045
+ADV
+Accuracy = 0.5
+Weighted Recall = 0.5
+Weighted Precision = 0.75
+Weighted F1 = 0.5416666666666667
+Macro Recall = 0.59375
+Macro Precision = 0.5625
+Macro F1 = 0.4791666666666667
+NOUN
+Accuracy = 0.5902527075812274
+Weighted Recall = 0.5902527075812274
+Weighted Precision = 0.5923391555769888
+Weighted F1 = 0.5896715360691773
+Macro Recall = 0.5913145539906104
+Macro Precision = 0.5918355301987015
+Macro F1 = 0.5899521016267187
+VERB
+Accuracy = 0.5384615384615384
+Weighted Recall = 0.5384615384615384
+Weighted Precision = 0.5370285166546849
+Weighted F1 = 0.5349820036204067
+Macro Recall = 0.5356020309477756
+Macro Precision = 0.5366978193146417
+Macro F1 = 0.5333760644629613

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/hh2/.cache/huggingface/transformers/7766c86e10505ed9b39af34e456480399bf06e35b36b8f2b917460a2dbe94e59.a984cf52fc87644bd4a2165f1e07e0ac880272c1e82d648b4674907056912bd7", "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a3bfd583ab13b41fa00ffec7b39941a5b85d772184d48c8393f0ce198f8cc4
+size 2811